Brex Agentic Access
Brex exposes 52 API operations that an AI agent could call, of which 27 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.
By consequence: 25 read, 25 write, 1 physical, and 1 safety-critical.
1 operation are classed safety-critical and should require human-in-the-loop approval at runtime.
Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.
API Evangelist recommendations, not provider rules. These classifications are generated heuristically from each operation's method, path and name. They suggest how an agent's access could be scoped. They are not authorization, approval or human-in-the-loop requirements that the provider enforces.
By consequence
Highest-consequence actions
The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.
| Method | Path | Consequence | Recommended human-in-loop |
|---|---|---|---|
| POST | /v2/cards/{id}/terminate | safety-critical | required |
| POST | /v2/cards/{id}/secure_email | physical | conditional |
Source
Agentic Access
generated: '2026-11-10'
method: generated
source: openapi/brex-budget-programs-api-openapi.yml, openapi/brex-budgets-api-openapi.yml,
openapi/brex-cards-api-openapi.yml, openapi/brex-companies-api-openapi.yml, openapi/brex-cost-centers-api-openapi.yml,
openapi/brex-departments-api-openapi.yml, openapi/brex-legal-entities-api-openapi.yml, openapi/brex-locations-api-openapi.yml,
openapi/brex-spend-limits-api-openapi.yml, openapi/brex-titles-api-openapi.yml, openapi/brex-users-api-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
audience per deployment. See research/curity/agentic-governance/.
summary:
operations: 52
by_action_class:
connected: 25
acting: 27
by_consequence:
read: 25
write: 25
physical: 1
safety-critical: 1
human_in_the_loop_required: 1
operations:
- path: /v1/budget_programs
method: get
operationId: listBudgetPrograms
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/budget_programs/{id}
method: get
operationId: getBudgetProgram
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/budgets
method: get
operationId: listV1Budgets
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/budgets
method: post
operationId: createV1Budget
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v1/budgets/{id}
method: get
operationId: getV1Budget
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/budgets/{id}
method: put
operationId: updateV1Budget
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v1/budgets/{id}/archive
method: post
operationId: archiveV1Budget
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/budgets
method: get
operationId: listV2Budgets
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v2/budgets
method: post
operationId: createV2Budget
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/budgets/{id}
method: get
operationId: getV2Budget
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v2/budgets/{id}
method: put
operationId: updateV2Budget
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/budgets/{id}/archive
method: post
operationId: archiveV2Budget
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/cards
method: get
operationId: listCardsByUserId
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- cards
- cards.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/cards
method: post
operationId: createCard
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- cards
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/cards/{id}
method: get
operationId: getCardById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- cards
- cards.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/cards/{id}
method: put
operationId: updateCard
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- cards
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/cards/{id}/lock
method: post
operationId: lockCard
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- cards
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/cards/{id}/pan
method: get
operationId: getCardNumber
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- cards.pan
token:
max-ttl: 3600
audit: none
- path: /v2/cards/{id}/secure_email
method: post
operationId: emailCardNumber
x-agentic-access:
action-class: acting
consequence: physical
subject: required
scope:
- cards.pan
audience: null
token:
max-ttl: 300
exchange: true
purpose-required: true
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/cards/{id}/terminate
method: post
operationId: terminateCard
x-agentic-access:
action-class: acting
consequence: safety-critical
subject: required
scope:
- cards
audience: null
token:
max-ttl: 120
exchange: true
purpose-required: true
proof-of-possession: true
escalation:
human-in-the-loop: required
audit: required
- path: /v2/cards/{id}/unlock
method: post
operationId: unlockCard
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- cards
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/company
method: get
operationId: getCompany
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- companies.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/cost_centers
method: get
operationId: listCostCenters
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- cost_centers
- cost_centers.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/cost_centers/{id}
method: get
operationId: getCostCenterById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- cost_centers
- cost_centers.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/departments
method: get
operationId: listDepartments
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- departments
- departments.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/departments
method: post
operationId: createDepartment
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- departments
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/departments/{id}
method: get
operationId: getDepartmentById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- departments
- departments.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/departments/{id}
method: put
operationId: updateDepartment
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- departments
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/departments/{id}
method: delete
operationId: deleteDepartment
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- departments
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/legal_entities
method: get
operationId: listLegalEntities
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- legal_entities
- legal_entities.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/legal_entities/{id}
method: get
operationId: getLegalEntity
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- legal_entities
- legal_entities.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/locations
method: get
operationId: listLocations
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- locations
- locations.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/locations
method: post
operationId: createLocation
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- locations
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/locations/{id}
method: get
operationId: getLocationById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- locations
- locations.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/locations/{id}
method: put
operationId: updateLocation
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- locations
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/locations/{id}
method: delete
operationId: deleteLocation
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- locations
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/spend_limits
method: get
operationId: listV2SpendLimits
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v2/spend_limits
method: post
operationId: createV2SpendLimit
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/spend_limits/{id}
method: get
operationId: getV2SpendLimit
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v2/spend_limits/{id}
method: put
operationId: updateV2SpendLimit
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/spend_limits/{id}/archive
method: post
operationId: archiveV2SpendLimit
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/titles
method: get
operationId: listTitles
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- titles
- titles.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/titles
method: post
operationId: createTitle
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- titles
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/titles/{id}
method: get
operationId: getTitleById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- titles
- titles.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/titles/{id}
method: put
operationId: updateTitle
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- titles
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/titles/{id}
method: delete
operationId: deleteTitle
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- titles
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/users
method: get
operationId: listUsers
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- users
- users.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/users
method: post
operationId: createUser
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- users
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/users/create
method: post
operationId: addUser
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- users
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /v2/users/me
method: get
operationId: getMe
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- users
- users.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/users/{id}
method: get
operationId: getUserById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
scope:
- users
- users.readonly
token:
max-ttl: 3600
audit: none
- path: /v2/users/{id}
method: put
operationId: updateUser
x-agentic-access:
action-class: acting
consequence: write
subject: required
scope:
- users
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
Work with this as data
Every access contract here is available over the APIs.io API and to AI agents over MCP. Agentic Access is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for agentic access
3 MCP tools reach this
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/search?q=brex-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/brex-agentic-access"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.